MCP server exposing Telora product operations to Claude Code
Soft block: AI-agent control surface
Warn by default; block when configured. Claude automatically runs those commands on matching events for projects using that user configuration.
AI security review
scanned · by lpm-firewall-ai
The manifest activates a postinstall script that silently adds commands to user-wide Claude hooks when Telora binaries are present. This is an unconsented install-time change to a broad agent control surface.
Installing the package when both Telora hook binaries are available on PATH.
Impact
Claude automatically runs those commands on matching events for projects using that user configuration.
Mechanism
The postinstall script adds commands to the PostToolUse and UserPromptSubmit hooks and writes the user-wide Claude settings file.
Policy narrative
During package installation, the postinstall script can change the user-wide Claude Code settings and add Telora commands to hooks that run on tool use and prompt submission. It does this without an affirmative consent check, extending the effect across projects using that configuration.
Avoid installing @telora/mcp-products@0.22.182. Remove it from direct dependencies and check your lockfile for transitive copies.
Choose an independently verified alternative or release. This report does not establish that other versions are safe.
If this version ran, check your AI agents' configuration and instruction files (the files this report lists) for changes you did not make, and remove them. This finding does not by itself establish malware intent.